Wireless local area network has a proliferation of nature leads to a very dangerous intrusion attack, known as Jamming. This Intrusion attack uses wireless technologies as a medium to launch Denial of service attack over these vulnerable networks. The recently jamming attack has been referred to as a very risky attack model. However, experts have been working on these security protocols. Although challengers with interior information and data privacy can execute a jamming attack which is hard to analyze, detect and protect. In this project, we have worked on particular problems of jamming attack in WLAN. In these jammed networks the attackers are active only for some time till the attack is planned as per the level of importance of the data/message shared and according to that attack will be executed. Here we have demonstrated a particular jamming attack by executing real-time packet transmission at the physical layer, to diminish these issues we have established three encryption methods of the physical layer characteristics for preventing from jamming attack. We examine the safety of the encryption hidden techniques and asses algorithmic and transmission overheads.

Predicting the price of used cars is one of the significant and interesting areas of analysis. As an increased demand in the second-hand car market, the business for both buyers and sellers has increased. For reliable and accurate prediction it requires expert knowledge about the field because of the price of the cars dependent on many important factors. This paper proposed a supervised machine learning model using KNN (K Nearest Neighbor) regression algorithm to analyze the price of used cars. We trained our model with data of used cars which is collected from the Kaggle website. Through this experiment, the data was examined with different trained and test ratios. As a result, the accuracy of the proposed model is around 85% and is fitted as the optimized model.

Sentiment analysis or determining the opinion is study about the people’s sentiment, emotions and opinion that is expressed in terms of text. It’s very popular because it helps us in understanding the opinions of other people. Which is the key influencer and important part of almost all human activities. The opinion of the people can be either positive or negative. The main objective of our work is to build a Machine Learning Ensemble model for Sentiment analysis. Ensemble strategies combine various learning algorithms to gain optimum performance. The Amazon Fine Food Reviews dataset has been used. The proposed model has been evaluated using various performance metrics such as Accuracy, Recall and Precision. Proposed system showed promising results when compared to individual base models.

In the present scenario, it is vital for any organization, especially the financial organizations, to understand customers and their financial dealings better. KYC is a process to verify identity and related details of corresponding customers. The current KYC mechanism has a severe concern in financial institutions as it requires separate ledger for the separate financial organizations. Every institution has its KYC process, which sometimes may include third-party, which may cause increased maintenance cost, time and redundancy. There is considerable wastage of costs in the form of opportunity cost, maintenance cost, customer verification cost and many more of around $27 million according to an economic survey. The current KYC process is very time-consuming, and it decreases the user experience. We have proposed an enhanced KYC system using blockchain technology to improve the existing KYC system. An inherent feature of the DLT is used to remove the third-party involvement, and smart contracts are used to build our logic in the mobility of the data. Blockchain technology has various types of cryptographic security which provide a safer place to transact over an unsecured channel. Using the facility of DLT, cryptography and consensus mechanism of blockchain, the proposed model of KYC process can optimize storing, updating, sharing of data and accessing operations along with enhanced security, transparency and privacy. It also enhances customer ownership and improves customer experience. It not only reduces the time duration and document update problem but also saves opportunity cost, aggregation, cost, maintenance cost and many more costs, which can affect the performance of any organization.

Coronavirus (COVID – 19) is a deadly virus that originally originated from Chinas Wuhan district around November last year. It has a deadly effect on the human respiratory system if the condition escalates. Currently, millions of people have been affected worldwide, and in countries like India, the cases are still on the rise. Due to an increased rise in cases, the testing facilities are struggling to keep up with the demand for testing, and medical experts are looking for alternate ways to speed up testing. In this paper, we have experimented with one such way by developing a CNN-based model to classify the chest X-ray images for the detection of coronavirus affected cases. For result analysis, we have applied CNN based VGG 16, VGG 19, and custom model. Further, we compare the result of these models based on accuracy. In this experimental analysis, VGG 19 model detected 99% of COVID-19 infected cases accurately as compared to VGG 16. This is entirely an experimental study and should not be used in real-life scenarios without an evaluation by medical experts and determining the effectiveness of this method.

In this paper fuzzy logic is used to predict first sight of distant relapse pattern in breast cancer patients after curative surgery with data. The overly expressed proteins, their structures and inhibitors are listed. Few of the proteins chosen are COX2, PgR, Nestin, SNAI 1, CK 5 and GATA3. Three primary sites of metastasis that is bone, brain and skin are chosen. The data elements are grouped into clusters and membership functions are thus obtained. A system of neurons, either artificial or organic in nature is trained with these relationship equations to estimate the first metastasis site. This network is tested for various available combinations of proteins. The table hence developed is defuzzified using lambda cut sets. These results are then compared to the ones obtained with the neuro fuzzy model. Keywords: Metastasis, proteins, inhibitors, artificial neural networks (ANN), fuzzy arithmetic, defuzzification.

Even with so many cryptographies present, homomorphic encryption has attracted wide attention from various scholars of this field due to its special and optimized performance. This lies down to the fact that the common cryptography methods cannot perform computations on encrypted data, and homomorphic encryption can. Also, homomorphic encryption provides automatically encrypted operation results. Since data breach is the biggest threat in the field of cloud computing, homomorphic encryption has a wide and very useful application in data security in a cloud environment. The main aim of this paper is to give an outline of the current security threats in the field of cloud computing and also throw light on the findings of homomorphic encryption, which include functional computations with operations such as addition, multiplication and then study them for the security of the cloud. The results produced only selected features vital for the prediction of cancer. Also, its performance has been paralleled against other factors such as Accuracy, Precision, Recall and Specificity, and Fmeasure. The experimental results show that the Decision Tree classifier outperforms all other classifiers with an accuracy of 94.7 % increased to 97% after Cuckoo Optimization.

In the era where we take internet access for granted, it is a setback to know that two out of three persons on the globe do not have access to internet connectivity. It is said that when internet penetration of a country increases by 10 percent, the GDP of the country can increase by 1.4 percent. Hence it becomes a quintessential task to have internet connectivity to cover as much as geographical area as possible. In this paper discusses technologies which help in providing internet access to places, where it is considered difficult to provide. Such places can be said to be when in transit in an aircraft or geographically tougher terrain where is difficult to lay optical fibres or cables. Airborne internet, Googles project LOON is a few of the things explained here. We can see how these technologies are implemented and discuss how various researches have contributed their ideas for improving connectivity. We see the applications and advantages of "network in the sky" here.

— A trending development in technologies demands for the higher performance machine to satisfy human and market needs. In today?s scenario, the world demands everything to be automated especially in the field of medical science, engineering and teaching fields etc. It is often seen that the boards which are used in schools and colleges are approximately 20 feet wide. And these chalkboards when completely written takes more than a minute to clean it manually. If a class continue for about one hour then about 10-12% time will be wasted in cleaning such a big board with a tiny duster. And the chalk dust obtained after erasing the board is also hazardous for human health. The “Automatic Board Cleaning Device” is a spectacular replacement of traditional duster. This project was selected by us to provide some comfort for teachers while cleaning the chalkboard. This automatic board cleaning system uses the aluminium track and wheels mechanism that moves horizontally for cleaning the chalkboard with the help of DC geared motors. It is also modified by adding a sprinkler and blower for wet wiping the board. Implementing this technique reduces the time consumption in cleaning the chalkboard manually as it can clean the board within a few seconds.

Smartphone usage has increased rigorously. Android is one of the most used operating systems in various smartphone worldwide. It is open-source and has chances of installing third-party applications without permission. Android is the most vulnerable operating system for a malware attack. This is a big threat to cyber security. In this paper, we make a dynamic analysis using android network traffic logs. We propose an ensemble modelled approach called XGBoost to detect malware and benign applications using the traffic. The proposed model is providing the accuracy of 92.28% and a Kappa coefficient of 0.83. Finally, some of the good set of features from android applications are outlined that helps us to label them as malware and benign. The proposed model is tested across various metrics and they are providing promising results.

With the increase in the number, types of sensors and their applications, the number of devices connected wirelessly to the internet are huge, bringing IoT technologies to the forefront. In a world where new wireless devices are added into the network every second, security and trust are of crucial importance. In this paper, a method to compute trust of the sensor node is proposed and the best route, among multiple routes, is selected to send a packet from source node to destination node via the most trusted route. The sensor data that is considered to decide the trust level of the nodes and best path are response time or end-to-end delay, many hops, energy consumed, residual energy, etc. The sensor network is a non-hierarchical network where the nodes are distributed over an area, the nodes are then clustered using the DBSCAN algorithm. The source node sends packets to all its neighbouring nodes and waits for the reply, based on the parameters stated above it selects the next-hop and keeps adding the trust values for that selected route. The process continues until it reaches the destination. The list of multiple routes based on cumulative trust value is found and the one with the highest trust is selected. This route can then be chosen for packet transfer.